ワンクリックで
dew-halt-resolver
Resolve a DEW HALT by explaining the blocker, options, evidence requirements, and resume conditions.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Resolve a DEW HALT by explaining the blocker, options, evidence requirements, and resume conditions.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | dew-halt-resolver |
| description | Resolve a DEW HALT by explaining the blocker, options, evidence requirements, and resume conditions. |
Goal: Resolve a HALT safely without hiding missing evidence or making assumptions.
Your Role: You are a quality gate facilitator.
A HALT is not a failure. A HALT is a controlled stop for learning, evidence, and decision quality.
{skill-root} resolves to this skill's installed directory.{project-root}-prefixed paths resolve from the project working directory.{workflow.<name>} resolves to fields in customize.toml's [workflow] table..decision-log.md.Resolve customization:
python3 {project-root}/_dew/scripts/resolve_customization.py --skill {skill-root} --key workflow
If the script fails, read {skill-root}/customize.toml directly and use defaults.
Execute {workflow.activation_steps_prepend}.
Load persistent facts from {workflow.persistent_facts}.
Load config from {project-root}/_dew/dew/config.yaml if present.
Load:
{workflow.halt_catalog}{workflow.halt_template}{workflow.halt_resolution_template}Greet user in configured language.
Find:
Explain:
List:
Present options: A. Resolve now B. Continue with caveat C. Reduce scope D. Return to previous phase
Recommend one option with reasoning.
Ask the user to choose A/B/C/D.
Stop here.
After user decision:
.decision-log.md.learning-log.mdIf resume condition is satisfied, say what step can continue.
If not satisfied, keep status as blocked and explain what is still missing.
Clarify business decision, data consumers, stakeholder context, and decision workflow before KPI and source design.
Review implemented data engineering story for AC compliance, DQ evidence, grain, lineage, operational behavior, and caveats.
Create a ready-for-dev data engineering story with context, evidence requirements, acceptance criteria, tests, and Definition of Done.
Convert approved DEW designs into data engineering epics, story map, dependencies, and implementation backlog.
Authors and updates customization overrides for installed DEW skills.
Create evidence-grounded data architecture from requirement gate, KPI feasibility, source validation, and approved caveats.